Apple M1 Microarchitecture Research by Dougall Johnson

Firestorm: Overview | Base Instructions | SIMD and FP Instructions
Icestorm:  Overview | Base Instructions | SIMD and FP Instructions

FCMGT (vector, 2D)

Test 1: uops

Code:

  fcmgt v0.2d, v0.2d, v1.2d
  movi v0.16b, 1
  movi v1.16b, 2

(no loop instructions)

1000 unrolls and 1 iteration

Retires: 1.000

Issues: 1.000

Integer unit issues: 0.000

Load/store unit issues: 0.000

SIMD/FP unit issues: 1.000

retire (01)cycle (02)0307181e3f4e51inst issue (52)~issue fp/simd (54)~dispatch fp/simd (57)huge thing fp/simd (5b)60696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op fp/simd (7e)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst neon or fp (9a)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100420371500082168725100010001000264680120182037203715723189510001000200020372037111001100073116111787100020382038203820382038
100420371600061168725100010001000264680120182037203715723189510001000200020372037111001100073116111787100020382038203820382038
1004203715002761168725100010001000264680120182037203715723189510001000200020372037111001100073116111787100020382038203820382038
1004203715002761168725100010001000264680120182037203715723189510001000200020372037111001100073116111787100020382038203820382038
1004203715002761168725100010001000264680120182037203715723189510001000200020372037111001100073116111787100020382038203820382038
100420371500061168725100010001000264680120182037203715723189510001000200020372037111001100073116111787100020382038203820382038
100420371500061168725100010001000264680120182037203715723189510001000200020372037111001100073116111787100020382038203820382038
100420371600061168725100010001000264680120182037203715723189510001000200020372037111001100073116111787100020382038203820382038
100420371500061168725100010001000264680120182037203715723189510001000200020372037111001100073116111787100020382038203820382038
100420371600361168725100010001000264680120182037203715723189510001000200020372037111001100073116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  fcmgt v0.2d, v0.2d, v1.2d
  movi v0.16b, 1
  movi v1.16b, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03090b1e3f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150000611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100107101161119791100001002003820038200382003820038
1020420037150000611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100107101161119791100001002003820038200382003820038
1020420037150000611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100037101161119791100001002003820038200382003820038
1020420037150000611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100107101161119791100001002003820038200382003820038
1020420037150000611968725101001001000010010000500284811420018200372003718422318745101002001000020020000200372003711102011009910010010000100107101161119791100001002003820038200382003820038
1020420037150000611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150000611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382023020038
1020420037150000611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100067101161119791100001002003820038200382003820038
10204200371500007261968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150000611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100371777101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03091e3f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)60696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371500061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640416441978510000102003820038200382003820038
1002420037150006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100111640416341978510000102003820038200382003820038
100242003715000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010057640416431978510000102003820038200382003820038
10024200371501061196872510010101001210100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640416431978510000102003820038200382003820038
10024200371500061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640416431978510000102003820038200382003820038
10024200371500061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000640416441978510000102003820038200382003820038
10024200371500061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000640416441978510000102003820038200382003820038
10024200371500061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640416341978510000102008520038200382003820038
1002420037150015536196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640416341978510000102003820038200382003820038
10024200371500061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640416441978510000102003820038200382003820038

Test 3: Latency 1->3

Code:

  fcmgt v0.2d, v1.2d, v0.2d
  movi v0.16b, 1
  movi v1.16b, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)030b18191e3f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)60696d6edispatch stall (70)72scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371500000474196872510100100100001001000050028476801200182003720037184220318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
10204200371500000477196872510100100100001001000050028476801200182003720037184227318745101002001000020020000200372003711102011009910010010000100037101161119791100001002003820038200382003820038
10204200371500000846196872510100100100001001000050028476801200182003720037184220318745101002001000020020000200372003711102011009910010010000100067101161119791100001002003820038200382003820038
1020420037149000010821968725101001001000010010000500284768012001820037200371842203187451010020010000200200002003720037111020110099100100100001003207101161119791100001002003820038200382003820038
1020420037150010061196872510100100100001001000050028476800200182003720037184220318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715000002061968725101001001000010010000500284768002001820037200371842203187451010020010000200200002003720037111020110099100100100001004207101161119791100001002003820038200382003820038
10204200371500000611968725101001001000010010000500284768002001820037200371842203187451010020010000200200002003720037111020110099100100100001003607101161119791100001002003820038200382003820038
1020420037150000061196872510100100100001001000050028476801200182003720037184220318745101002001000020020000200372003711102011009910010010000100207101161119791100001002003820038200382003820038
10204200371500000632196872510100100100001001000050028476800200182003720037184220318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420226150000961196872510100100100001001000050028476800200182003720037184220318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)031e3f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)60696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa8acbranch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)eb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715004951968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000064021622197850010000102003820038200382003820038
100242003715001471968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000064021622197850010000102003820038200382003820038
10024200371500611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000064021622197850010000102003820038200382003820038
10024200371500611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000064021622197850010000102003820038200382003820038
10024200371500611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000064021622197850010000102003820181200382003820038
10024200371500611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720084211002110910101000010100064021622197850010000102003820038200382003820038
100242003715001241968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000064021622197850010000102003820038200382003820038
10024200371500611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010391770064021622197850010000102003820038200382003820038
10024200371500611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000064021622197850010000102003820038200382003820038
10024200371500147196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001033630064021622197850010000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  fcmgt v0.2d, v8.2d, v9.2d
  fcmgt v1.2d, v8.2d, v9.2d
  fcmgt v2.2d, v8.2d, v9.2d
  fcmgt v3.2d, v8.2d, v9.2d
  fcmgt v4.2d, v8.2d, v9.2d
  fcmgt v5.2d, v8.2d, v9.2d
  fcmgt v6.2d, v8.2d, v9.2d
  fcmgt v7.2d, v8.2d, v9.2d
  movi v8.16b, 9
  movi v9.16b, 10

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 0.2505

retire (01)cycle (02)031e3f51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)60696b6d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa0a7a8a9acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802052005815007662580100100800001008000050064000002001902003820038997339996801002008000020016000020038200381180201100991001008000010000000051102161120035800001002003920039200392003920039
80204200381500402580100100800001008000050064000012001902003820038997339996801002008000020016000020038200381180201100991001008000010000000051101161120035800001002003920039200392003920039
80204200381500402580100100800001008000050064000002001902003820038997339996801002008000020016000020038200381180201100991001008000010000000051101161120035800001002003920039200392003920039
80204200381500610258010010080000100800005006400001200190200382003899733999680100200800002001600002003820038118020110099100100800001000010114051101161120035800001002003920039200392003920039
80204200381500402580100100800001008000050064000002001902003820038997339996801002008000020016000020038200381180201100991001008000010000000051101161120035800001002003920039200392003920039
8020420038150040258010010080000100800005006400001200190200382003899733999680100200800002001600002003820038118020110099100100800001000030051051101161120035800001002003920039200392003920039
80204200381500402580100100800001008000050064000012001902003820038997339996801002008000020016000020038200381180201100991001008000010000000051101161120035800001002003920039200392003920039
80204200381500402580100100800001008000050064000012001902003820038997339996801002008000020016000020038200381180201100991001008000010000000051101161120035800001002003920039200392003920039
80204200381500402580100100800001008000050064000002001902003820038997339996801002008000020016000020038200381180201100991001008000010000000151101161120035800001002003920039200392003920039
80204200381500402580100100800001008000050064000002001902003820038997339996801002008000020016000020038200381180201100991001008000010000250117051101161120035800001002003920039200392003920039

1000 unrolls and 10 iterations

Result (median cycles for code divided by count): 0.2505

retire (01)cycle (02)031e3f51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)60696d6edispatch stall (70)72scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa8cfd5d6dbddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200481500210258001010800001080000506400001200192003820038999603100188001020800002016000020038200381180021109101080000100502041602220035080000102003920039200392003920039
800242003815001051258001010800001080000506400001200192003820038999603100188001020800002016000020038200381180021109101080000100502021602220035080000102003920039200392003920039
80024200381500704258001010800001080000506400001200192003820038999603100188001020800002016000020038200381180021109101080000100502021602220035480000102003920039200392003920039
80024200381500690258001010800001080000506400001200192003820038999603100188001020800002016000020038200381180021109101080000100502021602220035080000102003920039200392003920039
8002420038149039258001010800001080000506400001200192003820038999603100188001020800002016000020038200381180021109101080000100502021602220035080000102003920039200392003920039
8002420038150039258001010800001080000506400001200192003820038999603100188001020800002016000020038200381180021109101080000102502021602220035080000102003920039200392003920039
8002420038150039258001010800001080000506400000200192003820038999603100188001020800002016000020038200381180021109101080000100502021602220035080000102003920039200392003920039
8002420038150081258001010800001080000506400001200192003820038999603100188001020800002016000020038200381180021109101080000100502021702220035180000102003920039200392003920039
80024200381500253258001010800001080000506400001200192003820038999603100188001020800002016000020038200381180021109101080000100502021602220035080000102003920039200392003920039
8002420038150039258001010800001080000506400001200192003820038999603100188001020800002016000020038200381180021109101080000100502021602220035080000102003920039200392003920039